INDEX

Explanations

instructions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¤§äºº

-0.33

 adultes

-0.28

ä¹ŁæĪĲä¸º

-0.28

 Tweets

-0.27

 sweets

-0.27

ä»ĵä½į

-0.27

iors

-0.27

urous

-0.25

éľĩ

-0.25

ÙģÙĤ

-0.24

POSITIVE LOGITS

aty

0.29

 Junction

0.25

à¸Ĭà¸Ļ

0.25

StatusLabel

0.25

Spacer

0.25

 insign

0.24

lyn

0.24

 damage

0.24

ÑģÐ¸

0.24

rov

0.24

Activations Density 0.002%

instructions

No Comments

No Known Activations